29 citations · 57 across the 28 of their papers we have counts for
17 papers · 1 filter
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
Masaki Kawamura, Nakamasa Inoue, Rintaro Yanagi +2
Contrastive vision-language pre-training frameworks such as CLIP have demonstrated impressive zero-shot performance across a range of vision-language tasks. Recent studies have sho…
AgroBench: Vision-Language Model Benchmark in Agriculture
Risa Shinoda, Nakamasa Inoue, Hirokatsu Kataoka +2
Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models (VLMs)…
AnimalClue: Recognizing Animals by their Traces
Risa Shinoda, Nakamasa Inoue, Iro Laina +2
Wildlife observation plays an important role in biodiversity conservation, necessitating robust methodologies for monitoring wildlife populations and interspecies interactions. Rec…
On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process
Shun Iwase, Shuya Takahashi, Nakamasa Inoue +3
The double descent phenomenon, which deviates from the traditional bias-variance trade-off theory, attracts considerable research attention; however, the mechanism of its occurrenc…
Formula-Supervised Visual-Geometric Pre-training
Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka +4
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object rec…
Rethinking Image Super-Resolution from Training Data Perspectives
Go Ohtani, Ryu Tadokoro, Ryosuke Yamada +7
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on com…
Scaling Backwards: Minimal Synthetic Pre-training?
Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada +6
Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, i…
Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering
Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda
Visual question answering (VQA) is the task of providing accurate answers to natural language questions based on visual input. Programmatic VQA (PVQA) models have been gaining atte…
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
Risa Shinoda, Ryo Hayamizu, Kodai Nakashima +3
Pre-training is a strong strategy for enhancing visual models to efficiently train them with a limited number of labeled images. In semantic segmentation, creating annotation masks…
Pre-training Vision Transformers with Very Limited Synthesized Images
Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima +3
Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has sho…
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
Sora Takashima, Ryo Hayamizu, Nakamasa Inoue +2
Formula-driven supervised learning (FDSL) has been shown to be an effective method for pre-training vision transformers, where ExFractalDB-21k was shown to exceed the pre-training…
Pre-training Vision Transformers with Formula-driven Supervised Learning
Hirokatsu Kataoka, Sora Takashima, Ryo Hayamizu +6
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k and can approach that of the JFT-300M d…
Can Vision Transformers Learn without Natural Images?
Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto +2
Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale datas…
Pre-training without Natural Images
Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto +5
Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding? The paper proposes a novel concept, Formula-driven…
Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka
We propose a novel network initialization method using Perlin noise for training image classification networks with a limited amount of data. Our main idea is to initialize the net…
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka +1
Unpaired image-to-image (I2I) translation has received considerable attention in pattern recognition and computer vision because of recent advancements in generative adversarial ne…
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
Thao Minh Le, Nakamasa Inoue, Koichi Shinoda
This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segment…